The emerging threat of ai-driven cyber attacks: A review

B Guembe, A Azeta, S Misra, VC Osamor… - Applied Artificial …, 2022‏ - Taylor & Francis
Cyberattacks are becoming more sophisticated and ubiquitous. Cybercriminals are
inevitably adopting Artificial Intelligence (AI) techniques to evade the cyberspace and cause …

Artificial intelligence, cyber-threats and Industry 4.0: Challenges and opportunities

A Bécue, I Praça, J Gama - Artificial Intelligence Review, 2021‏ - Springer
This survey paper discusses opportunities and threats of using artificial intelligence (AI)
technology in the manufacturing sector with consideration for offensive and defensive uses …

Trustworthy LLMs: A survey and guideline for evaluating large language models' alignment

Y Liu, Y Yao, JF Ton, X Zhang, RGH Cheng… - arxiv preprint arxiv …, 2023‏ - arxiv.org
Ensuring alignment, which refers to making models behave in accordance with human
intentions [1, 2], has become a critical task before deploying large language models (LLMs) …

The secret sharer: Evaluating and testing unintended memorization in neural networks

N Carlini, C Liu, Ú Erlingsson, J Kos… - 28th USENIX security …, 2019‏ - usenix.org
This paper describes a testing methodology for quantitatively assessing the risk that rare or
unique training-data sequences are unintentionally memorized by generative sequence …

A comprehensive survey of recent internet measurement techniques for cyber security

MS Pour, C Nader, K Friday, E Bou-Harb - Computers & Security, 2023‏ - Elsevier
As the Internet has transformed into a critical infrastructure, society has become more
vulnerable to its security flaws. Despite substantial efforts to address many of these …

The ai-based cyber threat landscape: A survey

N Kaloudi, J Li - ACM Computing Surveys (CSUR), 2020‏ - dl.acm.org
Recent advancements in artificial intelligence (AI) technologies have induced tremendous
growth in innovation and automation. Although these AI technologies offer significant …

False information on web and social media: A survey

S Kumar, N Shah - arxiv preprint arxiv:1804.08559, 2018‏ - arxiv.org
False information can be created and spread easily through the web and social media
platforms, resulting in widespread real-world impact. Characterizing how false information …

{Updates-Leak}: Data set inference and reconstruction attacks in online learning

A Salem, A Bhattacharya, M Backes, M Fritz… - 29th USENIX security …, 2020‏ - usenix.org
Machine learning (ML) has progressed rapidly during the past decade and the major factor
that drives such development is the unprecedented large-scale data. As data generation is a …

Unpacking the social media bot: A typology to guide research and policy

R Gorwa, D Guilbeault - Policy & Internet, 2020‏ - Wiley Online Library
Amid widespread reports of digital influence operations during major elections,
policymakers, scholars, and journalists have become increasingly interested in the political …

Deepfake text detection: Limitations and opportunities

J Pu, Z Sarwar, SM Abdullah, A Rehman… - … IEEE symposium on …, 2023‏ - ieeexplore.ieee.org
Recent advances in generative models for language have enabled the creation of
convincing synthetic text or deepfake text. Prior work has demonstrated the potential for …